Container cargo placement planning method, device and electronic equipment

Abstract

Embodiments of the present disclosure disclose a container cargo placement planning method, device and electronic equipment. A specific embodiment of the method includes: obtaining container information and a set of cargo information; voxelizing a virtual loading space model to obtain a sequence of voxelized space models; for each voxelized space model, taking the voxel granularity corresponding to the voxelized space model as a boundary constraint, performing virtual cargo loading on the voxelized space model according to the set of cargo information to obtain cargo placement planning information, and generating evaluation information for the cargo placement planning information; selecting, from the obtained set of cargo placement planning information, cargo placement planning information corresponding to evaluation information that satisfies a selection condition; and synchronizing target cargo placement planning information and target evaluation information to a visualization terminal. This embodiment realizes automated cargo placement planning, effectively improving placement planning efficiency and space utilization.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the fields of computer technology, target optimization, and especially cargo placement planning, specifically to cargo placement planning methods, apparatus, and electronic devices applied to containers. Background Technology

[0002] Land transport is a major mode of freight transport, with containers being the primary cargo carrier. In practice, when loading containerized cargo, it is common to encounter goods of different sizes, types, and categories being packed in less-than-container-load (LCL) containers. Based on this, the loading and unloading personnel rely heavily on their experience to plan the placement of the cargo.

[0003] However, the above methods have the following technical problems: manual methods rely heavily on human experience, the placement planning is time-consuming, and the space utilization rate is difficult to guarantee. Summary of the Invention

[0004] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0005] Some embodiments of this disclosure propose a cargo placement planning method, apparatus, and electronic equipment for use in containers to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide a cargo placement planning method applied to containers. The method includes: acquiring a set of container information and a set of cargo information, wherein the container information represents the available loading space corresponding to a container to be loaded, and the cargo information in the cargo information set corresponds to non-mutually exclusive cargo to be loaded; spatial voxelizing a virtual loading space model to obtain a sequence of voxelized spatial models, wherein the virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence correspond to different voxel granularities; for each voxelized spatial model in the sequence, using the aforementioned... The voxel granularity corresponding to the voxelized spatial model is the boundary constraint. Based on the above cargo information set, virtual cargo loading is performed on the voxelized spatial model to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. Cargo placement planning information that meets the screening conditions is selected from the obtained cargo placement planning information set as target cargo placement planning information, and the evaluation information corresponding to the target cargo placement planning information is used as target evaluation information. The above target cargo placement planning information and the above target evaluation information are synchronized to the visualization terminal.

[0007] Secondly, some embodiments of this disclosure provide a cargo placement planning device for containers. The device includes: an acquisition unit configured to acquire a set of container information and cargo information, wherein the container information represents the available loading space corresponding to a container to be loaded, and the cargo information in the cargo information set corresponds to non-mutually exclusive cargo to be loaded; a spatial voxelization unit configured to perform spatial voxelization on a virtual loading space model to obtain a sequence of voxelized spatial models, wherein the virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence of voxelized spatial models correspond to different voxel granularities; and a virtual cargo loading and generation unit configured to load and generate cargo for each voxelized space model in the sequence of voxelized spatial models. The post-space model, using the voxel granularity corresponding to the aforementioned voxelized post-space model as boundary constraints, performs virtual cargo loading on the aforementioned voxelized post-space model based on the aforementioned cargo information set, obtaining cargo placement planning information and generating evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. The filtering unit is configured to filter cargo placement planning information that meets the filtering conditions from the obtained cargo placement planning information set as target cargo placement planning information, and to use the evaluation information corresponding to the target cargo placement planning information as target evaluation information. The synchronization unit is configured to synchronize the aforementioned target cargo placement planning information and the aforementioned target evaluation information to the visualization terminal.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] The above embodiments of this disclosure have the following beneficial effects: The cargo placement planning method applied to containers according to some embodiments of this disclosure achieves automated cargo placement planning, effectively improving placement planning efficiency and space utilization. Specifically, the reason for low placement efficiency and difficulty in guaranteeing space utilization is that manual methods rely heavily on human experience. Based on this, the cargo placement planning method applied to containers according to some embodiments of this disclosure first obtains a set of container information and cargo information, wherein the container information represents the available loading space corresponding to the container to be loaded, and the cargo information in the cargo information set corresponds to non-mutually exclusive cargo to be loaded. This yields the available loading space of the container to be loaded or loaded, and cargo information related to the cargo to be loaded. Second, the virtual loading space model is spatially voxelized to obtain a sequence of voxelized spatial models, wherein the virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence correspond to different voxel granularities. Conventional methods primarily optimize the target based on cargo and container information sets, often requiring the design of complex optimization functions. Therefore, this disclosure utilizes spatial voxelization at different voxel granularities to facilitate subsequent virtual cargo filling. The boundary relationships between the cargo to be loaded and the voxel units in the virtual loading space model are used to assess the rationality of the placement. Next, for each voxelized spatial model in the aforementioned sequence, using the voxel granularity corresponding to the voxelized spatial model as boundary constraints, virtual cargo loading is performed on the voxelized spatial model based on the aforementioned cargo information set. This yields cargo placement planning information and generates evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. Through virtual cargo loading, corresponding cargo placement planning information and evaluation information are generated without actual cargo loading, facilitating adjustments to the placement plan. Furthermore, from the obtained set of goods placement planning information, goods placement planning information that meets the corresponding evaluation criteria is selected as target goods placement planning information, and the evaluation information corresponding to the target goods placement planning information is selected as target evaluation information. This process is used to select the optimal placement planning information and corresponding evaluation information. Finally, the above target goods placement planning information and target evaluation information are synchronized to the visualization terminal. This method achieves automated goods placement planning, effectively improving placement planning efficiency and space utilization. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1 This is a flowchart of some embodiments of the cargo placement planning method applied to containers according to the present disclosure;

[0013] Figure 2 This is a schematic diagram of the spatial voxelization process;

[0014] Figure 3 It is a rendered image of a 3D visualization model of cargo loading;

[0015] Figure 4 This is a schematic diagram of the structure of some embodiments of the cargo placement planning device applied to containers according to the present disclosure;

[0016] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0020] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0022] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] refer to Figure 1 The flowchart 100 illustrates some embodiments of a cargo placement planning method applied to containers according to the present disclosure. This cargo placement planning method applied to containers includes the following steps:

[0024] Step 101: Obtain the container information and cargo information set.

[0025] In some embodiments, the entity executing the cargo placement planning method applied to containers (e.g., a computing device) can obtain the aforementioned set of container information and cargo information via a wired or wireless connection. In practice, container information can be obtained by reading a container information database, and cargo information can be obtained by reading a cargo information database. The container information database can be a database storing information about the containers to be loaded. The cargo information database can be a database storing information about the cargo to be loaded.

[0026] The container information represents the available loading space corresponding to the container to be loaded with goods. Specifically, the container information may include the container specifications and available space specifications corresponding to the container to be loaded with goods. The goods information set corresponds to non-mutually exclusive goods to be loaded. Specifically, because different types of goods may affect each other, the goods to be loaded corresponding to the goods information in the goods information set should meet the restriction that they can be loaded into the same container. For example, electronic products and powdered goods are mutually exclusive goods to be loaded (because powdered goods may seep into electronic products, potentially damaging them). Similarly, textiles, paper, and grease are mutually exclusive goods to be loaded (because grease may seep into textiles or paper during transportation). Furthermore, metal materials and corrosive goods are mutually exclusive goods to be loaded (because corrosive goods may corrode metal materials). For example, precision instruments and goods that vibrate are mutually exclusive (because vibration during transportation can damage the precision of precision instruments). Therefore, when acquiring a set of goods information, the set can be filtered from the goods information database based on pre-defined mutual exclusion conditions between goods. The goods information can include: goods type, packaging type, packaging load capacity, goods loading constraints, goods specifications, goods placement direction, goods number, goods quantity, and a list of order numbers. Packaging type represents the type of packaging corresponding to the goods to be loaded (e.g., paper packaging, wooden frame packaging, etc.). Packaging load capacity represents the maximum load-bearing capacity of the goods packaging when stacked. Goods loading constraints represent the loading constraints on the goods to be loaded (e.g., mutually exclusive goods types). Goods specifications represent the specifications of the goods (especially, goods specifications can be represented by goods packaging specifications). Goods placement direction represents the allowed placement direction of the goods. Goods number represents the unique identifier of the goods. The list of order numbers represents the list of order numbers related to the goods.

[0027] It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (Ultra Wide Band) connections, and other currently known or future wireless connection methods.

[0028] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0029] Step 102: Perform spatial voxelization on the virtual loading space model to obtain a voxelized space model sequence.

[0030] In some embodiments, the aforementioned execution entity may perform spatial voxelization on the virtual loading space model to obtain a voxelized space model sequence.

[0031] The virtual loading space model is a 3D model corresponding to the container information. The voxelized spatial models in the above sequence correspond to different voxel granularities.

[0032] In practice, firstly, since container information can include the container specifications and available space specifications of the container to be loaded, a corresponding 3D loading model can be constructed within 3D simulation software as a virtual loading space model. Then, the virtual loading space model is voxelized at different voxel granularities to obtain a sequence of voxelized space models corresponding to different voxel granularities. See [example description missing] for an example. Figure 2 The diagram illustrates the spatial voxelization process. By voxelizing the virtual loading space model, a voxelized spatial model composed of 3×7×3 voxel units (voxel granularity) can be obtained. Specifically, since the specifications of different goods to be loaded may vary, the planning results may fall into a local optimum when combining voxel unit boundaries for virtual goods loading. Therefore, this disclosure sets different voxel granularities for spatial voxelization during the spatial voxelization stage.

[0033] In some optional implementations of certain embodiments, the aforementioned execution entity performs spatial voxelization on the virtual loading space model to obtain a voxelized space model sequence, including:

[0034] Step S1: For each piece of cargo information in the above cargo information set, generate cargo specification features based on the cargo specification information included in the above cargo information.

[0035] Since cargo specification information represents cargo specifications (e.g., length, width, height), the cargo specification information included in the cargo information can be normalized through numerical normalization to serve as the corresponding cargo specification feature.

[0036] Step S2: Perform cargo specification clustering based on the obtained cargo specification feature set to obtain an initial specification information set.

[0037] Among them, the initial specification information represents the average value of the cargo specifications corresponding to the same cluster.

[0038] In practice, firstly, a clustering algorithm (e.g., K-means algorithm, hierarchical clustering algorithm, etc.) can be used to cluster the cargo specifications based on the obtained cargo specification feature set, resulting in at least one cluster. Then, the mean value of the cargo specifications corresponding to at least one cargo information item of each cluster is determined as the initial specification information, thus obtaining the initial specification information set.

[0039] Step S3: For each initial specification information in the above initial specification information set, generate a scaled specification information group according to the preset scaling coefficient sequence and the above initial specification information.

[0040] In practice, when spatial voxelizing a virtual loading space, a set of voxelization granularities can be preset for spatial voxelization processing. However, since the goods to be transported may differ each time, although the method of preset voxelization granularities can quickly achieve spatial voxelization, it may still lead to the planning results getting stuck in a local optimum when loading virtual goods. Therefore, this disclosure dynamically generates the corresponding voxel granularity based on the cargo specification information of each batch of goods to be transported. In addition, since the initial specification information represents the average cargo specification information of the corresponding cluster, in order to ensure the effective loading of all goods to be loaded, the voxel granularity should avoid being too large or too small, and too discrete. Therefore, a set of preset scaling coefficients are used to scale the initial specification information to expand the voxel granularity.

[0041] Step S4: Using the scaled specification information in the obtained scaled specification information set as the voxel granularity, perform voxel segmentation on the above virtual loading space model to generate a voxelized space model, and obtain the above voxelized space model sequence.

[0042] In practice, for each scaled specification information in the set of scaled specification information, the virtual loading space model is segmented into voxels with the scaled specification information as the voxel unit corresponding to the voxel granularity to generate a voxelized space model.

[0043] As an example, the scaled-up specification information can be: A×B×C. Therefore, this can be used as the voxel granularity to perform voxel segmentation on the virtual loading space model, resulting in 3×7×3 voxel units with a voxel granularity of A×B×C.

[0044] Step 103: For each voxelized spatial model in the voxelized spatial model sequence, using the voxel granularity corresponding to the voxelized spatial model as the boundary constraint, virtual cargo loading is performed on the voxelized spatial model according to the cargo information set to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information.

[0045] In some embodiments, the execution entity performs virtual cargo loading on each voxelized spatial model in the voxelized spatial model sequence, using the voxel granularity corresponding to the voxelized spatial model as a boundary constraint, based on the cargo information set, to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information.

[0046] The evaluation information includes: loading space utilization, cargo stability information set, and center of gravity offset. Loading space utilization represents the container's space utilization rate. Cargo stability information represents the stability of the cargo after placement, based on the cargo placement planning information. Center of gravity offset represents the offset between the overall center of gravity of multiple cargoes to be loaded and the corresponding center of gravity of the container, based on the cargo placement planning information.

[0047] In practice, firstly, cargo to be loaded can be selected from the cargo information set whose specifications are less than or equal to the voxel granularity corresponding to the voxelized spatial model. Then, using algorithms such as genetic algorithms and swarm intelligence optimization algorithms (e.g., ant colony optimization), the selected cargo to be loaded with specifications less than or equal to the voxel granularity corresponding to the voxelized spatial model is placed according to a placement plan, resulting in corresponding cargo placement planning information. Next, given the known placement positions of the cargo to be loaded according to the cargo placement planning information, the loading space utilization and center of gravity offset are calculated using container information. Furthermore, since there is often a strict correspondence between the cargo to be loaded and the voxel granularity, under the placement plan corresponding to the cargo placement planning information, the cargo to be loaded often corresponds to at least one voxel unit. Therefore, the distance between the cargo to be loaded and the center of gravity of the corresponding voxel unit can be calculated to obtain the corresponding cargo stability. In particular, the closer the cargo is to the center of gravity of the voxel unit, the higher the cargo stability.

[0048] In some optional implementations of certain embodiments, the execution entity, for each voxelized spatial model in the voxelized spatial model sequence, uses the voxel granularity corresponding to the voxelized spatial model as a boundary constraint, and performs virtual cargo loading on the voxelized spatial model according to the cargo information set to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information, including:

[0049] Step S1: Using the voxel granularity corresponding to the above voxelized spatial model as boundary constraints, virtual cargo loading is performed according to the pre-set permutation and combination rules and the above cargo information set to generate a candidate placement planning information set.

[0050] Among them, the candidate placement planning information in the aforementioned candidate placement planning information set corresponds to different placement planning results. The permutation and combination rules can represent preset planning rules. For example, permutation and combination rules may include: prioritizing the laying of lower-level goods, prioritizing the planning of heavy objects, and prioritizing the planning of the placement of large-sized goods.

[0051] In practice, the specifications of goods selected for placement planning should be less than or equal to the voxel granularity. Therefore, algorithms such as genetic algorithms and swarm intelligence optimization algorithms (e.g., ant colony optimization) can be used, with the voxel granularity corresponding to the aforementioned voxelized spatial model as the boundary constraint, to perform virtual cargo loading according to pre-set permutation and combination rules and the aforementioned cargo information set, generating a candidate placement planning information set. Through different iterative optimizations, multiple placement planning schemes can be obtained, thus yielding multiple candidate placement planning information sets.

[0052] Step S2: For each candidate placement plan in the above candidate placement plan information set, perform the following processing steps based on the candidate placement plan information:

[0053] Step S21: Based on the candidate placement planning information, generate the voxel unit features corresponding to each voxel unit in the above voxelized spatial model, and obtain the voxel unit feature matrix.

[0054] The voxel unit features are constructed based on the location of the voxel unit and the corresponding cargo information. First, since the number of voxel units and their relative positions in the voxelized spatial model are known, the relative position of each voxel unit can be extracted. Second, after placement planning, some cargo to be placed may be located within voxel units; therefore, the cargo specifications of cargo located within voxel units and the distance between the cargo and the center of gravity of the voxel unit can be extracted. Finally, the relative positions, cargo specifications of cargo located within voxel units, and the distance between the cargo and the center of gravity of the voxel unit are used to construct the voxel unit features. These features are then filled using only a matrix according to the relative positions of the voxel units in the voxelized spatial model to obtain the voxel unit feature matrix.

[0055] Step S22: Generate initial evaluation information for candidate placement planning information based on the voxel unit feature matrix and the pre-built evaluation information generation model.

[0056] Among them, the initial evaluation information represents the evaluation of the placement of goods corresponding to the candidate placement planning information.

[0057] In practice, the evaluation information generation model can consist of a discriminator. During the training phase, the generator and discriminator are trained using labeled placement planning information and corresponding evaluation information. The generator combines the voxel unit feature matrix corresponding to the labeled placement planning information to generate placement planning information, while the discriminator generates corresponding evaluation information based on the generated placement planning information. After training, the discriminator evaluates the candidate placement planning information to obtain the corresponding initial evaluation information. Specifically, since the voxel unit feature matrix has three-dimensional characteristics, the generator adopts a graph neural network + multiple SoftMax layers architecture. The graph neural network is used to capture the matrix features of the voxel unit feature matrix. The multiple SoftMax layers output the initial evaluation information based on the extracted matrix features.

[0058] Step S23: In response to the convergence of the initial evaluation information or the number of iterations being greater than or equal to the number of iterations, the candidate placement planning information is determined as the goods placement planning information, and the initial evaluation information is determined as the goods placement planning information.

[0059] In practice, the constructed candidate placement planning information may get stuck in local optima due to limitations in the placement combination rules and the optimization function corresponding to the algorithm. Therefore, an evaluation information generation model is used to determine the rationality of the goods placement in the candidate placement planning information. In addition, to avoid repeated iterations affecting efficiency, an iteration count is set to control the maximum threshold of iterations.

[0060] Step S3: In response to the initial evaluation information not converging or not reaching the iteration number, optimize the candidate placement planning information based on the initial evaluation information to obtain optimized placement planning information. Use the optimized placement planning information as candidate placement planning information and execute the above processing steps again.

[0061] In practice, when the initial evaluation information fails to converge, the abnormal locations can be locally replanned and optimized using genetic algorithms, swarm intelligence optimization algorithms, etc., in step S1 of step 103, in combination with the initial evaluation information to obtain optimized placement planning information.

[0062] In some optional implementations of certain embodiments, the execution entity generates initial evaluation information for the candidate placement planning information based on the voxel unit feature matrix and a pre-built evaluation information generation model, including:

[0063] Step S221: Based on the candidate placement planning information and the above container information, determine the loading space utilization rate included in the initial evaluation information.

[0064] First, since the goods to be placed in the candidate placement planning information are known and do not overlap, the total volume of the goods to be placed in the candidate placement planning information can be determined by combining the corresponding goods specification information. Then, the ratio of the total volume of the goods to be placed in the candidate placement planning information to the available loading space corresponding to the container information is determined as the loading space utilization rate included in the initial evaluation information.

[0065] Step S222: Determine the center of gravity of the goods based on the candidate placement planning information.

[0066] In practice, since the goods to be placed in the candidate placement planning information are known, the center of gravity of the overall goods to be placed in the candidate placement planning information can be obtained by combining the relevant goods information, including the goods specifications.

[0067] Step S223: Determine the distance between the cargo's center of gravity and the center of gravity of the available loading space corresponding to the above container information, as the center of gravity offset included in the initial evaluation information.

[0068] In practice, the center of gravity offset consists of offset components in three dimensions: X, Y, and Z. First, a center of gravity vector can be constructed by combining the cargo's center of gravity and the center of gravity of the available loading space corresponding to the container information mentioned above. Then, the center of gravity vector is projected along the X, Y, and Z dimensions respectively, and the vector components are taken to obtain the center of gravity offset included in the initial evaluation information.

[0069] Step S224: Divide the voxel unit feature matrix along the vertical and horizontal dimensions respectively to obtain a set of voxel unit feature submatrices.

[0070] In practice, the voxel unit feature matrix is ​​a holistic description of the cargo to be loaded corresponding to the candidate placement planning information. However, the candidate placement planning information may have suboptimal local locations. For example, there may be instability or insufficient space utilization along the vertical or horizontal dimensions. Therefore, by segmenting the voxel unit feature matrix along the vertical and horizontal dimensions, a set of voxel unit feature submatrices is obtained, thereby obtaining a local feature description from the vertical or horizontal dimensions.

[0071] Step S225: Based on the above set of voxel unit feature submatrices and the above evaluation information generation model, generate the initial evaluation information set including cargo stability information.

[0072] In practice, for each voxel unit feature submatrix in the voxel unit feature submatrix set, the corresponding cargo stability information is generated by using the voxel unit feature submatrix as input to the evaluation information generation model. The cargo stability information characterizes the placement stability among multiple cargoes to be loaded along the vertical or horizontal dimension.

[0073] Step 104: Select the corresponding evaluation information that meets the selection criteria from the obtained set of goods placement planning information, and use it as the target goods placement planning information; and use the evaluation information corresponding to the target goods placement planning information as the target evaluation information.

[0074] In some embodiments, the aforementioned execution entity may select from the obtained set of goods placement planning information the goods placement planning information whose corresponding evaluation information meets the selection criteria, as the target goods placement planning information, and use the evaluation information corresponding to the target goods placement planning information as the target evaluation information.

[0075] In practice, firstly, appropriate weights can be assigned to loading space utilization, center of gravity offset (specifically, the center of gravity offset can be converted into distance values ​​along the X, Y, and Z directions), and cargo stability information set, and a score value corresponding to each cargo placement planning information can be determined by weighted summation. Then, the cargo placement planning information with the highest corresponding score is selected from the cargo placement planning information as the target cargo placement planning information.

[0076] Step 105: Synchronize the target cargo placement planning information and target evaluation information to the visualization terminal.

[0077] In some embodiments, the aforementioned implementing entity can synchronize the target cargo placement planning information and target evaluation information to the visualization terminal.

[0078] Among them, the visualization terminal can be a control terminal used to display the three-dimensional visualization of the placement of goods corresponding to the target goods placement planning information.

[0079] In some optional implementations of some embodiments, the above method further includes:

[0080] Step S1: Based on the above target cargo placement planning information and the above virtual loading space model, generate a visual 3D model of cargo loading.

[0081] In practice, since the target cargo placement planning information represents the cargo location planning of the cargo to be loaded, it is possible to combine the cargo specification information included in the corresponding cargo information to perform three-dimensional rendering on the basis of the virtual loading space model to obtain a visual three-dimensional model of cargo loading.

[0082] As an example, see Figure 3 The image shown is a rendering of a 3D visualization model of cargo loading, illustrating the arrangement of items inside the container from a top-down perspective.

[0083] Step S2: Based on the cargo stability information set included in the above target evaluation information, perform virtual cargo thermal value mapping on the above cargo loading visualization 3D model to obtain the thermal value mapped 3D model.

[0084] Among them, the thermal value is positively correlated with the cargo stability information represented by cargo stability information.

[0085] In practice, cargo stability information represents the cargo stability among multiple cargoes to be loaded in either a vertical or horizontal dimension. Therefore, thermal value mapping can be used to map the cargoes to be loaded that are involved in the cargo stability information.

[0086] Step S3: After mapping the above thermal values, the 3D model is synchronized to the above visualization terminal.

[0087] In practice, the model can be updated in real time to synchronize the 3D model mapped from the above thermal values ​​to the above visualization terminal.

[0088] Step S4: In response to receiving the cargo location update instruction initiated by the visualization terminal, update the three-dimensional model after the above thermal value mapping according to the cargo location update instruction to obtain the updated three-dimensional model.

[0089] In practice, depending on actual needs, further optimization of the cargo position may be required manually. Therefore, by combining the cargo position update command initiated by the visualization terminal, the position of the cargo to be loaded in the 3D model after thermal value mapping is optimized in real time to obtain the updated 3D model.

[0090] Step S5: Based on the updated 3D model, update the target cargo placement planning information to obtain updated cargo placement planning information, and generate updated evaluation information for the above cargo placement planning information.

[0091] In practice, when the location of the goods to be loaded changes, the target goods placement planning information can be updated by combining the updated 3D model to obtain the updated goods placement planning information. A corresponding new voxel unit feature matrix can be constructed, and the updated evaluation information can be generated by combining the evaluation information to generate the model.

[0092] Step S6: Update the above-mentioned updated 3D model, the above-mentioned updated cargo placement planning information, and the above-mentioned updated evaluation information to the above-mentioned visualization terminal.

[0093] In some optional implementations of some embodiments, the above method further includes:

[0094] Step S1: In response to receiving the cargo placement instruction sent by the visualization terminal, generate a cargo loading task based on the updated cargo placement planning information.

[0095] In practice, when a cargo placement instruction is received, it indicates that cargo should be loaded according to the updated cargo placement plan information, thus requiring the generation of a corresponding cargo loading task.

[0096] Step S2: Add the above cargo loading task to the cargo loading task sequence.

[0097] Among them, the cargo loading task sequence is a message queue that executes cargo loading tasks sequentially.

[0098] In practice, cargo loading tasks can be added to the cargo loading task sequence according to their priority.

[0099] Step S3: In response to the cargo loading task being at the beginning of the cargo loading task sequence, associate the loading equipment corresponding to the aforementioned cargo loading task.

[0100] In practice, when a cargo loading task is at the beginning of a cargo loading task sequence, it indicates that the task needs to be executed, thus requiring the association of the corresponding loading equipment. In particular, different types of cargo may involve different loading equipment; therefore, it is necessary to combine the cargo information involved in the loading task to associate the corresponding loading equipment.

[0101] Step S4: In response to the completion of the association, the above cargo loading task is distributed to the loading equipment.

[0102] In practice, cargo loading tasks can be distributed to loading equipment in a parallel manner.

[0103] Step S5: Obtain the real-time location of the container corresponding to the above container information.

[0104] In practice, containers can be equipped with positioning devices, thus allowing the acquisition of container information and the real-time location of the container.

[0105] Step S6: Generate a geofence based on the real-time location.

[0106] Among them, a geofence can be an electronic fence centered on a real-time location.

[0107] Step S7: In response to the loading equipment moving the cargo to be loaded into the geofence, update the loading progress corresponding to the cargo loading task and synchronize the updated loading progress to the visualization terminal.

[0108] The above embodiments of this disclosure have the following beneficial effects: The cargo placement planning method applied to containers according to some embodiments of this disclosure achieves automated cargo placement planning, effectively improving placement planning efficiency and space utilization. Specifically, the reason for low placement efficiency and difficulty in guaranteeing space utilization is that manual methods rely heavily on human experience. Based on this, the cargo placement planning method applied to containers according to some embodiments of this disclosure first obtains a set of container information and cargo information, wherein the container information represents the available loading space corresponding to the container to be loaded, and the cargo information in the cargo information set corresponds to non-mutually exclusive cargo to be loaded. This yields the available loading space of the container to be loaded or loaded, and cargo information related to the cargo to be loaded. Second, the virtual loading space model is spatially voxelized to obtain a sequence of voxelized spatial models, wherein the virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence correspond to different voxel granularities. Conventional methods primarily optimize the target based on cargo and container information sets, often requiring the design of complex optimization functions. Therefore, this disclosure utilizes spatial voxelization at different voxel granularities to facilitate subsequent virtual cargo filling. The boundary relationships between the cargo to be loaded and the voxel units in the virtual loading space model are used to assess the rationality of the placement. Next, for each voxelized spatial model in the aforementioned sequence, using the voxel granularity corresponding to the voxelized spatial model as boundary constraints, virtual cargo loading is performed on the voxelized spatial model based on the aforementioned cargo information set. This yields cargo placement planning information and generates evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. Through virtual cargo loading, corresponding cargo placement planning information and evaluation information are generated without actual cargo loading, facilitating adjustments to the placement plan. Furthermore, from the obtained set of goods placement planning information, goods placement planning information that meets the corresponding evaluation criteria is selected as target goods placement planning information, and the evaluation information corresponding to the target goods placement planning information is selected as target evaluation information. This process is used to select the optimal placement planning information and corresponding evaluation information. Finally, the above target goods placement planning information and target evaluation information are synchronized to the visualization terminal. This method achieves automated goods placement planning, effectively improving placement planning efficiency and space utilization.

[0109] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a cargo placement planning device applied to containers. These device embodiments are similar to... Figure 1Corresponding to the method embodiments shown, the cargo placement planning device applied to containers can be specifically applied to various electronic devices.

[0110] like Figure 4 As shown, a cargo placement planning device 400 for containers in some embodiments includes: an acquisition unit 401, a spatial voxelization unit 402, a virtual cargo loading and generation unit 403, a filtering unit 404, and a synchronization unit 405. The acquisition unit 401 is configured to acquire a set of container information and cargo information. The container information represents the available loading space corresponding to the container to be loaded, and the cargo information in the cargo information set corresponds to non-exclusive cargo to be loaded. The spatial voxelization unit 402 is configured to perform spatial voxelization on the virtual loading space model to obtain a sequence of voxelized spatial models. The virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence correspond to different voxel granularities. The virtual cargo loading and generation unit 403 is configured to... For each voxelized spatial model in the above voxelized spatial model sequence, using the voxel granularity corresponding to the above voxelized spatial model as the boundary constraint, virtual cargo loading is performed on the above voxelized spatial model according to the above cargo information set to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. The filtering unit 404 is configured to filter cargo placement planning information that meets the filtering conditions from the obtained cargo placement planning information set as target cargo placement planning information, and to use the evaluation information corresponding to the target cargo placement planning information as target evaluation information. The synchronization unit 405 is configured to synchronize the above target cargo placement planning information and the above target evaluation information to the visualization terminal.

[0111] It is understandable that the units described in the cargo placement planning device 400 applied to containers are related to the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the cargo placement planning device 400 applied to containers and the units contained therein, and will not be repeated here.

[0112] The following is for reference. Figure 5 It illustrates a schematic diagram of the structure of an electronic device (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 5As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0113] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0114] In one embodiment, the processor is configured to run a computer program stored in a memory to perform the following steps: acquiring a set of container information and cargo information, wherein the container information represents the available loading space corresponding to a container to be loaded with cargo, and the cargo information in the cargo information set corresponds to non-exclusive cargo to be loaded; spatial voxelizing the virtual loading space model to obtain a sequence of voxelized spatial models, wherein the virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence of voxelized spatial models correspond to different voxel granularities; for each voxelized spatial model in the sequence of voxelized spatial models, the above... The voxel granularity corresponding to the voxelized spatial model is the boundary constraint. Based on the above cargo information set, virtual cargo loading is performed on the voxelized spatial model to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. Cargo placement planning information that meets the screening conditions is selected from the obtained cargo placement planning information set as target cargo placement planning information, and the evaluation information corresponding to the target cargo placement planning information is selected as target evaluation information. The target cargo placement planning information and the target evaluation information are synchronized to the visualization terminal.

[0115] This disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to the various embodiments of the methods described above.

[0116] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0117] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0118] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A cargo placement planning method applied to containers, characterized in that, include: Obtain a set of container information and cargo information, wherein the container information represents the available loading space corresponding to the container to be loaded, and the cargo to be loaded corresponding to the cargo information in the cargo information set should meet the restriction that it can be loaded into the same container; The virtual loading space model is spatially voxelized to obtain a sequence of voxelized spatial models. The virtual loading space model is a three-dimensional model corresponding to the container information. The voxelized spatial models in the sequence of voxelized spatial models correspond to different voxel granularities. For each voxelized spatial model in the voxelized spatial model sequence, the voxel granularity corresponding to the voxelized spatial model is used as the boundary constraint. Based on the cargo information set, virtual cargo loading is performed on the voxelized spatial model to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set and center of gravity offset. The center of gravity offset represents the offset between the overall center of gravity of multiple cargoes to be loaded involved in the cargo placement planning information and the center of gravity of the corresponding container. From the obtained set of goods placement planning information, select the goods placement planning information that meets the selection criteria and use it as the target goods placement planning information; and use the evaluation information corresponding to the target goods placement planning information as the target evaluation information. The target cargo placement planning information and the target evaluation information are synchronized to the visualization terminal.

2. The cargo placement planning method applied to containers according to claim 1, characterized in that, The method further includes: Based on the target cargo placement planning information and the virtual loading space model, a visual 3D model of cargo loading is generated; Based on the cargo stability information set included in the target evaluation information, a virtual cargo thermal value mapping is performed on the cargo loading visualization 3D model to obtain a 3D model after thermal value mapping, wherein the thermal value is positively correlated with the cargo stability represented by the cargo stability information; The 3D model mapped from the thermal values ​​is synchronized to the visualization terminal. In response to receiving a cargo location update instruction initiated by the visualization terminal, the model of the three-dimensional model after thermal value mapping is updated according to the cargo location update instruction to obtain the updated three-dimensional model; Based on the updated 3D model, the target cargo placement planning information is updated to obtain updated cargo placement planning information, and updated evaluation information for the cargo placement planning information is generated. The updated 3D model, the updated cargo placement planning information, and the updated evaluation information are updated to the visualization terminal.

3. The cargo placement planning method applied to containers according to claim 2, characterized in that, The method further includes: In response to receiving a cargo placement instruction from the visualization terminal, a cargo loading task is generated based on the updated cargo placement planning information; Add the cargo loading task to the cargo loading task sequence; In response to a cargo loading task being at the beginning of a cargo loading task sequence, the loading equipment corresponding to the cargo loading task is associated; Once the association is complete, the cargo loading task is distributed to the loading equipment; Obtain the real-time location of the container corresponding to the container information; Generate a geofence based on the real-time location; In response to the loading equipment moving the cargo to be loaded into the geofence, the loading progress corresponding to the cargo loading task is updated, and the updated loading progress is synchronized to the visualization terminal.

4. The cargo placement planning method applied to containers according to claim 3, characterized in that, The process of spatial voxelizing the virtual loading space model to obtain a voxelized space model sequence includes: For each piece of cargo information in the cargo information set, cargo specification features are generated based on the cargo specification information included in the cargo information; Based on the obtained set of cargo specification features, cargo specification clustering is performed to obtain an initial set of specification information. For each initial specification information in the initial specification information set, a scaled specification information group is generated according to the preset scaling factor sequence and the initial specification information. Using the scaled specification information in the obtained scaled specification information set as the voxel granularity, the virtual loading space model is segmented into voxels to generate a voxelized space model, thus obtaining the voxelized space model sequence.

5. The cargo placement planning method applied to containers according to claim 4, characterized in that, For each voxelized spatial model in the voxelized spatial model sequence, using the voxel granularity corresponding to the voxelized spatial model as a boundary constraint, and based on the cargo information set, virtual cargo loading is performed on the voxelized spatial model to obtain cargo placement planning information, and evaluation information for the cargo placement planning information is generated, including: Using the voxel granularity corresponding to the voxelized spatial model as boundary constraints, virtual cargo loading is performed according to the pre-set arrangement and combination rules and the cargo information set to generate a candidate placement planning information set, wherein the candidate placement planning information in the candidate placement planning information set corresponds to different placement planning results; For each candidate placement planning information in the candidate placement planning information set, the following processing steps are performed based on the candidate placement planning information: Based on the candidate placement planning information, voxel unit features corresponding to each voxel unit in the voxelized spatial model are generated to obtain a voxel unit feature matrix. The voxel unit features are composed of the voxel unit's location and the cargo information corresponding to the voxel unit. Based on the voxel unit feature matrix and the pre-built evaluation information generation model, initial evaluation information for candidate placement planning information is generated. In response to the convergence of the initial evaluation information or the current iteration number being greater than or equal to the iteration number, the candidate placement planning information is determined as the goods placement planning information, and the initial evaluation information is determined as the goods placement planning information. In response to the initial evaluation information not converging or the current iteration number not reaching the iteration number, the candidate placement planning information is optimized based on the initial evaluation information to obtain optimized placement planning information. The optimized placement planning information is then used as candidate placement planning information, and the processing steps are executed again.

6. The cargo placement planning method applied to containers according to claim 5, characterized in that, The initial evaluation information for the candidate placement planning information is generated based on the voxel unit feature matrix and the pre-constructed evaluation information generation model, including: Based on the candidate placement planning information and the container information, the loading space utilization rate, including the initial evaluation information, is determined. Determine the center of gravity of the goods based on the candidate placement plan information; The distance between the cargo's center of gravity and the center of gravity of the available loading space corresponding to the container information is determined and used as the center of gravity offset included in the initial evaluation information. The voxel unit feature matrix is ​​segmented along both the vertical and horizontal dimensions to obtain a set of voxel unit feature submatrices. Based on the set of feature submatrices of the voxel units and the evaluation information generation model, an initial evaluation information set including cargo stability information is generated.

7. A cargo placement planning device applied to containers, characterized in that, include: The acquisition unit is configured to acquire a set of container information and cargo information, wherein the container information represents the available loading space corresponding to the container to be loaded, and the cargo to be loaded corresponding to the cargo information in the cargo information set should meet the restriction that it can be loaded into the same container; A spatial voxelization unit is configured to perform spatial voxelization on a virtual loading space model to obtain a sequence of voxelized spatial models, wherein the virtual loading space model is a three-dimensional model corresponding to the container information, and the voxelized spatial models in the sequence of voxelized spatial models correspond to different voxel granularities. The virtual cargo loading and generation unit is configured to, for each voxelized spatial model in the voxelized spatial model sequence, use the voxel granularity corresponding to the voxelized spatial model as a boundary constraint, and perform virtual cargo loading on the voxelized spatial model according to the cargo information set to obtain cargo placement planning information and generate evaluation information for the cargo placement planning information. The evaluation information includes: loading space utilization rate, cargo stability information set, and center of gravity offset. The center of gravity offset represents the offset between the overall center of gravity of the multiple cargoes to be loaded involved in the cargo placement planning information and the center of gravity of the corresponding container. The filtering unit is configured to filter out the corresponding evaluation information that meets the filtering conditions from the obtained set of goods placement planning information, and use the evaluation information corresponding to the target goods placement planning information as the target evaluation information. The synchronization unit is configured to synchronize the target cargo placement planning information and the target evaluation information to the visualization terminal.

8. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the computer program, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images